CLuP-Based Dual-Deconvolution in Automotive ISAC Scenarios

2025-03-28

AI Summary

This work addresses the double-blind deconvolution problem in vehicular integrated sensing and communication (ISAC), where both the radar channel and communication message are unknown. We propose a joint parameter estimation framework combining controllable relaxation (CLuP) with nuclear norm regularization. Leveraging known radar waveforms and communication channels—i.e., asymmetric prior knowledge—the method jointly models the problem in both delay-Doppler and angular domains and solves it via iterative optimization, enabling robust joint estimation of range, velocity, and angle. Compared to conventional maximum-likelihood approaches, the proposed algorithm significantly reduces computational complexity while ensuring real-time performance and estimation stability under high-mobility and strong-noise conditions. To the best of our knowledge, this is the first work to introduce CLuP into double-blind deconvolution for vehicular ISAC. The resulting solution offers a scalable, low-overhead, and tightly integrated sensing-communication paradigm for vehicle-infrastructure cooperative systems.

Technology Category

• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Learning & Optimization for CV

Application Category

• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Accurate target parameter estimation of range, velocity, and angle is essential for vehicle safety in advanced driver assistance systems (ADAS) and autonomous vehicles. To enable spectrum sharing, ADAS may employ integrated sensing and communications (ISAC). This paper examines a dual-deconvolution automotive ISAC scenario where the radar waveform is known but the propagation channel is not, while in the communications domain, the channel is known but the transmitted message is not. Conventional maximum likelihood (ML) estimation for automotive target parameters is computationally demanding. To address this, we propose a low-complexity approach using the controlled loosening-up (CLuP) algorithm, which employs iterative refinement for efficient separation and estimation of radar targets. We achieve this through a nuclear norm restriction that stabilizes the problem. Numerical experiments demonstrate the robustness of this approach under high-mobility and noisy automotive environments, highlighting CLuP's potential as a scalable, real-time solution for ISAC in future vehicular networks.

Problem

• Accurate estimation of vehicle range, velocity, and angle for ADAS safety
• Low-complexity dual-deconvolution in ISAC with unknown radar channel and message
• Robust target parameter estimation in high-mobility noisy automotive environments

Innovation

• CLuP algorithm for low-complexity estimation
• Nuclear norm restriction stabilizes problem
• Iterative refinement separates radar targets